RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: AI Radio. Generated commentary on the latest Artificial Intelligence papers.
Tom: We're looking at the paper: "RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery".
Paper summary: Tom: So we're looking at this paper called RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery, and the core idea here is that it builds a new framework for satellite imagery reconstruction by using the Rational Polynomial Camera or RPC model directly instead of just simplifying it.
Jane: That sounds complicated. So what are they claiming is different from the existing Gaussian Splatting methods? What's the main problem they're trying to solve?
Lu: The main problem is that prior satellite Gaussian Splatting methods often replace the complex RPC model with simpler perspective or affine camera models, and this substitution introduces geometric errors during both reconstruction and projection.
Meng: So if you use a simple approximation instead of the real RPC model, the resulting three dee scene geometry gets warped <ref:2606.06690#pg1>. That's not good for accurate mapping.
Tom: Exactly. And this paper claims that RPC-GS avoids these approximations by projecting the Gaussian means and covariances directly through the RPC model during the splatting process itself, which is a big deal for accuracy.
Jane: So how do they achieve this? It sounds like they need a way to connect their splatting coordinates to real satellite images using that complex RPC math.
Lu: They embed the RPC model into a chain of carefully selected geo-coordinate transformations that map the splatting-suitable local scene coordinates all the way up to global geodetic coordinates and finally project them into image coordinates through that RPC model.
Meng: Mapping scene coordinates to global ones sounds like it involves a lot of coordinate conversions, which can get messy when you're dealing with Earth models. What about the math part?
Tom: The paper introduces something called a numerically robust, RPC-native covariance projection using Jacobians to handle that mapping. They derive a solver-independent Jacobian by inverting the local differential of the forward mapping for those nonlinear transformations from global Cartesian coordinates to ellipsoidal geodetic coordinates.
Jane: A Jacobian sounds like it's how they calculate how much things stretch or bend when you move from one coordinate system to another, which is super important since it's a nonlinear transformation.
Paper summary: Lu: They also introduce a metric ray-based depth formulation specifically for RPC cameras, which lets them do RPC-consistent front-to-back alpha compositing even though the RPC models don't inherently have a depth coordinate built in.
Meng: So they are tackling two different problems at once: the way they map coordinates and how they correctly order the layers when painting the final image. That sounds like a lot of technical work to get right.
Tom: And to put it all together, their main contribution is providing the first unified Gaussian Splatting benchmark for RPC, perspective, and affine camera models for satellite imagery so you can directly compare those camera-model choices against each other.
Jane: That comparison is really useful. So what are the actual results they show when they test this RPC-GS framework? Are these improvements just theoretical, or do they show real performance gains?
Lu: On the DFC2019 dataset, their native RPC renderer achieves the lowest altitude mean error, and it reduces that mean altitude error over perspective and affine approximations by twenty-nine point six percent compared to DFC2019 <ref:2606.06690#pg3>.
Meng: Twenty-nine point six percent reduction is a solid number, but what about the other dataset they used? Are these gains consistent across different satellite imagery benchmarks?
Tom: They also saw reductions on the IARPA2016 dataset, where they achieved reductions of nine point nine percent and thirty-seven point nine percent respectively <ref:2606.06690#pg3>. That shows consistency across different testing sets for their method.
Jane: So, to summarize what we've heard about RPC-GS: it’s a Gaussian Splatting system that uses the native RPC model, overcomes geometric errors by using Jacobian-based projections, and they have shown measurable improvements over standard perspective and affine approximations on benchmark datasets like DFC2019.
Lu: They did successfully map splatting-compatible normalized local scene coordinates to global geodetic coordinates and then project them into image coordinates via the RPC model in a way that is numerically robust.
Meng: From an engineering standpoint, the real question is how much overhead this introduces. Since they're doing the RPC projection in Python while rasterization uses the three deeGS CUDA renderer, what does that look like when you try to scale this up for production <ref:2606.06690#pg1>?
Paper summary: Tom: The paper acknowledges that standard Gaussian Splatting usually relies on Jacobian-based covariance projection which locally approximates nonlinear mappings as affine, and they point out that applying this approximation to both the geodetic transform and the RPC projection might introduce errors if first-order propagation isn't sufficient.
Jane: So, what's the caveat there? What are they admitting about where their current method might fall short?
Lu: They note that recent alternatives, like the Unscented Transform from Wu et al., could provide more accurate uncertainty propagation, which is a direction for future work. Also, they mention that having RPC projection and splatting performed in Python while the rasterization uses the three deeGS CUDA renderer introduces some computational overhead <ref:2606.06690#pg1>.
Meng: I'm worried about that overhead when you think about deploying this to handle massive amounts of satellite data at scale. If it slows down the training pipeline significantly, it might not be practical for real-time applications where I work.
Tom: The paper does provide code to support future research in the satellite imaging domain, which is encouraging because it means the mechanics are ready for others to build upon and test against real-world traffic.
Jane: So, thinking about what this means for us listening right now—it suggests that instead of just using simple camera models for satellite imagery, we can use these more complex RPC models to get much higher accuracy in reconstructing the three dee scene geometry <ref:2606.06690#pg1>.
Lu: The implication is that by embedding the RPC model correctly into the coordinate chain and deriving robust projections, we can achieve significantly lower altitude errors when reconstructing scenes from satellite data compared to simpler methods.
Meng: It means for users who rely on this reconstruction for applications like remote sensing or mapping, they could get much more precise three dee models without needing to switch entirely to a completely new type of rendering pipeline <ref:2606.06690#pg1>.
Tom: The paper's work is focused on showing that native RPC rendering is the way to go for accuracy in satellite imagery Gaussian Splatting.
Jane: So, the big picture here seems to be moving away from approximations and toward using the actual mathematical model of how those sensors capture light, which leads to better results when comparing different camera models.
Conclusion: Tom: So we're wrapping up this look at RPC-GS, the Gaussian Splatting framework that uses native Rational Polynomial Camera rendering for satellite imagery.
Jane: It really boils down to taking that complex camera model and using it directly in the splatting process instead of just a simple approximation.
Lu: The authors are showing how they embed the RPC model into a whole chain of coordinate transformations, mapping local scene coordinates all the way to real global geodetic coordinates and projecting them into image coordinates using that specific RPC math.
Meng: From an engineering standpoint, what’s the main thing you get out of this whole setup? What’s the practical takeaway for someone trying to build a system?
Tom: The practical thing is accuracy. They're not just tweaking parameters; they've shown this native approach achieves the lowest altitude reconstruction error on major satellite benchmark datasets.
Jane: That means when you use this method, your three dee model of the scene will be much closer to what’s actually out there in space than if you used a simpler perspective or affine camera model.
Lu: They quantified that improvement too. On the DFC2019 dataset, they reduced the mean altitude error by twenty-nine point six percent compared to those other methods.
Meng: Twenty-nine point six percent is a solid number, but I gotta ask what happens when you try to run this at scale. Does the whole coordinate transformation chain slow down your training pipeline?
Tom: The paper does admit that running the RPC projection in Python while using a CUDA renderer for the final rasterization adds some computational overhead.
Jane: So they’re not ignoring that, and they’re flagging where things might get slow if you try to deploy it to handle massive satellite data.
Lu: They pointed out that standard methods use Jacobian-based covariance projection which is essentially a local approximation, and if you apply that approximation twice—once for the coordinate chain and once for the RPC projection—you can introduce errors.
Meng: So they’re acknowledging a trade-off here where you get better geometry but maybe at the cost of complexity or computation time.
Tom: Exactly. They also mentioned that newer techniques like the Unscented Transform could give you even more accurate uncertainty propagation down the line.
Jane: The big implication is that for anyone working on satellite photogrammetry, it shows that sticking closer to the actual sensor math, like using RPC, gives you a much tighter reconstruction of where things are in three dee space.
Lu: It’s about moving away from guessing how to approximate the camera model and actually using the correct mathematical description of how those sensors work.
Tom: So, this RPC-GS paper is a strong argument for why researchers should prioritize using the native RPC formulation when building Gaussian Splatting systems for satellite imagery.
Jane: It sets a new standard for accuracy in this field, but we still have to figure out how to make it fast enough for real-world deployment.
Valentin Wagner, Sebastian Bullinger, Christoph Bodensteiner, Michael Arens
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation
cs.CV
Submitted: 2026-06-04
Updated: 2026-11-18
Comments: Accepted at NeurIPS 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Importance score: 89/100
The gist: RPC-GS introduces RPC-GS, the first Gaussian Splatting framework for satellite imagery that operates natively with Rational Polynomial Camera (RPC) models The RPC model is the de facto standard for…
Key concepts
- Rational Polynomial Camera (RPC) Model
- This is the standard mathematical model used to represent the complex imaging geometry of modern pushbroom satellite sensors. It accurately captures the intricate projection mathematics of these sensors, avoiding geometric errors common in simpler camera models.
- Native RPC Renderer
- This is a custom rendering method within Gaussian Splatting that uses the RPC model directly. Instead of approximating it with simpler models, this renderer handles the complex sensor geometry natively, leading to more accurate 3D reconstructions.
- Coordinate System Chain
- A defined sequence of coordinate systems (Scene → ENU → ECEF → Geodetic → Image) used to map scene coordinates into global geodetic and image coordinates. This chain ensures that the splatting process correctly handles the complex transformations between different spatial references.
- Covariance Projection via Jacobian
- The method for projecting the uncertainty (covariance) of a 3D Gaussian point onto the 2D image plane. RPC-GS derives this projection using Jacobians from the forward mapping, which is numerically robust and solver-independent for nonlinear transformations.
Terminology
Summary
RPC-GS introduces RPC-GS, the first Gaussian Splatting framework for satellite imagery that operates natively with Rational Polynomial Camera (RPC) models The RPC model is the de facto standard for representing the complex imaging geometry of modern pushbroom satellite sensors This method avoids geometric errors introduced by approximating the RPC model with perspective or affine camera models Our native RPC renderer consistently achieves the lowest reconstruction error on leading satellite benchmark datasets, improving mean altitude error over perspective and affine approximations by 29. p. 06% and 63.8% on DFC2019
Motivation for Native RPC Rendering
The paper addresses the limitation of existing Gaussian Splatting methods, which often approximate the complex Rational Polynomial Camera (RPC) model with simpler perspective or affine camera models This substitution inherently introduces systematic errors during the projection and covariance splatting process Prior work has shown that replacing complex RPC models with simple approximations potentially introduces errors that degrade the geometry reconstructed by Gaussian Splatting The authors motivate a native RPC formulation for Gaussian Splatting that uses the sensor model directly, removing the need for camera conversion and image warping
Key Technical Contributions
The main contributions of the work are detailed in several points
-
Integrate the RPC model into a carefully chosen geo-coordinate transformation chain, enabling the mapping of splatting-compatible normalized local scene coordinates to global geodetic coordinates and their projection into image coordinates via the RPC model
-
Derive a numerically robust, RPC-native covariance projection using Jacobians, obtaining a solver-independent Jacobian by inverting the local differential of the forward mapping for nonlinear transformations
-
Introduce a metric ray-based depth formulation for RPC cameras, enabling RPC-consistent front-to-back alpha compositing despite the absence of an inherent depth coordinate in RPC models
-
Provide the first unified Gaussian Splatting benchmark of RPC, perspective, and affine camera models for satellite imagery
Coordinate System Transformations
The paper establishes a chain of coordinate systems to map splatting-suitable scene coordinates to image coordinates This chain is defined as Scene → ENU → ECEF → Geodetic → Image The transformation from Geodetic to ECEF involves a nonlinear forward mapping defined by Equation (5) To handle the non-uniform scaling of geodetic coordinates, the authors parameterize Gaussians in a local East-North-Up (ENU) frame anchored at an observer point
Covariance and Depth Projection
The paper adapts standard Gaussian Splatting's covariance projection by viewing the Scene → Image mapping as a composition of coordinate transformations and propagating the covariance using the corresponding Jacobian J image←scene The final 2 × 2 covariance matrix is derived from this chain, where the Jacobian J image←scene is the product of Jacobians of each transformation in the chain Furthermore, a metric ray-based depth parameterization inspired by SatNeRF is introduced to enable RPC-consistent front-to-back ordering during rasterization
Experimental Evaluation
The performance of RPC-GS is evaluated against perspective and affine camera approximations using a shared framework with identical training and evaluation settings The results on the DFC2019 dataset show that native RPC achieves the lowest altitude MAE, reducing mean altitude error over perspective and affine approximations by 29.6% and 63.8% on DFC2019 These improvements are also observed on the IARPA2016 dataset, with reductions of 9. p. 69% and 37.9% respectively
Limitations and Future Directions
The authors acknowledge that standard Gaussian Splatting typically uses Jacobian-based covariance projection, which approximates nonlinear mappings locally as affine This approximation is applied to both the ECEF → geodetic transform and the RPC projection, and may introduce errors when first-order propagation is insufficient Recent alternatives such as the Unscented Transform Wu et al. [2024] could provide more accurate uncertainty propagation and are a promising direction for future work The implementation also has computational overhead, as RPC projection and splatting are performed in Python while rasterization uses the 3DGS CUDA renderer
Conclusion
In this work, RPC-GS achieves the lowest altitude reconstruction error by embedding the RPC model in a suitable geo-coordinate transformation chain The framework provides a unified benchmark comparing RPC, perspective, and affine camera models for satellite imagery It successfully reduces mean altitude error over perspective and affine approximations by 29.6% and 37.9% on DFC2019 and IARPA2016 respectively The work is released with code to support future research in the satellite imaging domain
References
Luca Savant Aira, Gabriele Facciolo, and Thibaud Ehret. Gaussian splatting for efficient satellite image photogrammetry Nan Bai, Anran Yang, Hao Chen, and Chun Du. p. 9 Satgs: Remote sensing novel view synthesis using multi- temporal satellite images with appearance-adaptive 3dgs Marc Bosch, Zachary Kurtz, Shea Hagstrom, and Myron Brown. p. 9 A multiple view stereo benchmark for satellite imagery Pierrick Bournez, Luca Savant Aira, Thibaud Ehret, and Gabriele Facciolo. p. 9 Eogs++: Earth observation gaussian splatting with internal camera refinement and direct panchromatic rendering Sebastian Bullinger, Christoph Bodensteiner, and Michael Arens. p. 9 3d surface reconstruction from multi-date satellite images Tom G. p. 9 Farr, Paul A. p. 9 Rosen, Edward Caro, Robert Crippen, Riley Duren, Scott Hensley, Michael Kobrick, Mimi Paller, Ernesto Rodriguez, Ladislav Roth, David Seal, Scott Shaffer, Joanne Shimada, Jeffrey Umlandd, Marian Werner, Michael Oskin, Douglas Burbank, and Douglas Alsdorf. p. 9 The shuttle radar topography mission Jian Gao, Jin Liu, and Shunping Ji. p. 9 Rational polynomial camera model warping for deep learning based satellite multi-view stereo matching Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, and Shenghua Gao. p. 9 2d gaussian splatting for geometrically accurate radiance fields Bernhard Kerbl, Georgios Kopanas, Thomas Leimkuehler, and George Drettakis. p. 9 3d gaussian splatting for real-time radiance field rendering Jonáš Kulhánek, Songyou Peng, Zuzana Kúkelová, Marc Pollefeys, and Torsten Sattler. p. 9 Wildgaussians: 3d gaussian splatting in the wild Bertrand Le Saux, Naoto Yokoya, Ronny Hänsch, and Myron Brown. p. 9 Data fusion contest 2019 (dfc2019) Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai, Wei-Cheng Chang, Chung-Ho Wu, Jiewen Chan, Zhenjun Zhao, Chieh Hubert Lin, and Yu-Lun Liu. p. 9 Skyfall-gs: Synthesizing immersive 3d urban scenes from satellite imagery Alfred Leick, L. p. 9 B. Rapoport, and Dmitry V. p. 9 Tatarnikov. p. 9 Gps satellite surveying: Leick/gps satellite surveying Roger Marí, Gabriele Facciolo, and Thibaud Ehret. p. 9 Sat-nerf: Learning multi-view satellite photogrammetry with transient objects and shadow modeling using rpc cameras Roger Marí, Gabriele Facciolo, and Thibaud Ehret. p. 9 Multi-date earth observation nerf: The detail is in the shadows NGA. p. 9 WORLD GEODETIC SYSTEM 1984 - Its Definition and Relationships with Local Geodetic Systems J. p. 9 Sanz Subirana, J. p. 4 p. 4 M. Juan Zornoza, and M. Hernández-Pajares. Transformations between ecef and enu coordinates J. p. 5 Sanz Subirana, J. M. Juan Zornoza, and M. Hernández-Pajares Ellipsoidal and cartesian coordinates conversion C Vincent Tao and Yong Hu. p. 1 A comprehensive study of the rational function model for photogrammetric processing Wolfgang Torge and Jürgen Müller. p. 4 p. 4 p. 4 p. 4 p. 4 p. 4 Geodesy R J You. p. 4 p. 4 p. 4 p. 4 p. 4 p. 4 Transformation of cartesian to geodetic coordinates without iterations Jiawei Zhang, Xiangrong Zhang, Junxiao Li, Xu Tang, Tianyang Zhang, Guanchun Wang, Feixiang Liu, and Licheng Jiao. p. 1 p. 1 p. 1 p. 1 p. 1 p. 1 Shadow-aware 3d gaussian splatting for multi-view satellite images Kai Zhang, Jin Sun, and Noah Snavely. p. 9 p. 9 p. 9 p. 9 p. 9 p. 9 Leveraging vision reconstruction pipelines for satellite imagery Qingyuan Zhou, Yue Gong, Weidong Yang, Jiaze Li, Yeqi Luo, Baixin Xu, Shuhao Li, Ben Fei, and Ying He. Mgsr: 2d/3d mutual-boosted gaussian splatting for high-fidelity surface reconstruction under various light conditions Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, and Markus H Gross. Surface splatting NGA. p. 3 p. 3 p. 3 p. 3 p. 3 p. 3 WORLD GEODETIC SYSTEM 1984 - Its Definition and Relationships with Local Geodetic Systems J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Transformations between ecef and enu coordinates J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Ellipsoidal and cartesian coordinates conversion C Vincent Tao and Yong Hu. p. 9 p. 9 p. 9 p. 9 p. 9 A comprehensive study of the rational function model for photogrammetric processing Wolfgang Torge and Jürgen Müller. Geodesy R J You. Transformation of cartesian to geodetic coordinates without iterations Jiawei Zhang, Xiangrong Zhang, Junxiao Li, Xu Tang, Tianyang Zhang, Guanchun Wang, Feixiang Liu, and Licheng Jiao. Shadow-aware 3d gaussian splatting for multi-view satellite images Kai Zhang, Jin Sun, and Noah Snavely. Leveraging vision reconstruction pipelines for satellite imagery Qingyuan Zhou, Yue Gong, Weidong Yang, Jiaze Li, Yeqi Luo, Baixin Xu, Shuhao Li, Ben Fei, and Ying He. Mgsr: 2d/3d mutual-boosted gaussian splatting for high-fidelity surface reconstruction under various light conditions Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, and Markus H Gross. Surface splatting NGA. WORLD GEODETIC SYSTEM 1984 - Its Definition and Relationships with Local Geodetic Systems J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Transformations between ecef and enu coordinates J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Ellipsoidal and cartesian coordinates conversion C Vincent Tao and Yong Hu. A comprehensive study of the rational function model for photogrammetric processing Wolfgang Torge and Jürgen Müller. Geodesy R J You. Transformation of cartesian to geodetic coordinates without iterations Jiawei Zhang, Xiangrong Zhang, Junxiao Li, Xu Tang, Tianyang Zhang, Guanchun Wang, Feixiang Liu, and Licheng Jiao. Shadow-aware 3d gaussian splatting for multi-view satellite images Kai Zhang, Jin Sun, and Noah Snavely. Leveraging vision reconstruction pipelines for satellite imagery Qingyuan Zhou, Yue Gong, Weidong Yang, Jiaze Li, Yeqi Luo, Baixin Xu, Shuhao Li, Ben Fei, and Ying He. Mgsr: 2d/3d mutual-boosted gaussian splatting for high-fidelity surface reconstruction under various light conditions Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, and Markus H Gross. Surface splatting NGA. WORLD GEODETIC SYSTEM 1984 - Its Definition and Relationships with Local Geodetic Systems J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Transformations between ecef and enu coordinates J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Ellipsoidal and cartesian coordinates conversion C Vincent Tao and Yong Hu. A comprehensive study of the rational function model for photogrammetric processing Wolfgang Torge and Jürgen Müller. Geodesy R J You. Transformation of cartesian to geodetic coordinates without iterations Jiawei Zhang, Xiangrong Zhang, Junxiao Li, Xu Tang, Tianyang Zhang, Guanchun Wang, Feixiang Liu, and Licheng Jiao. Shadow-aware 3d gaussian splatting for multi-view satellite images Kai Zhang, Jin Sun, and Noah Snavely. Leveraging vision reconstruction pipelines for satellite imagery Qingyuan Zhou, Yue Gong, Weidong Yang, Jiaze Li, Yeqi Luo, Baixin Xu, Shuhao Li, Ben Fei, and Ying He. Mgsr: 2d/3d mutual-boosted gaussian splatting for high-fidelity surface reconstruction under various light conditions Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, and Markus H Gross. Surface splatting NGA. WORLD GEODETIC SYSTEM 1984 - Its Definition and Relationships with Local Geodetic Systems J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Transformations between ecef and enu coordinates J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Ellipsoidal and cartesian coordinates conversion C Vincent Tao and Yong Hu. A comprehensive study of the rational function model for photogrammetric processing Wolfgang Torge and Jürgen Müller. Geodesy R J You. Transformation of cartesian to geodetic coordinates without iterations Jiawei Zhang, Xiangrong Zhang, Junxiao Li, Xu Tang, Tianyang Zhang, Guanchun Wang, Feixiang Liu, and Licheng Jiao. Shadow-aware 3d gaussian splatting for multi-view satellite images Kai Zhang, Jin Sun, and Noah Snavely. Leveraging vision reconstruction pipelines for satellite imagery Qingyuan Zhou, Yue Gong, Weidong Yang, Jiaze Li, Yeqi Luo, Baixin Xu, Shuhao Li, Ben Fei, and Ying He. Mgsr: 2d/3d mutual-boosted gaussian splatting for high-fidelity surface reconstruction under various light conditions Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, and Markus H Gross. Surface splatting NGA. WORLD GEODETIC SYSTEM 1984 - Its Definition and Relationships with Local Geodetic Systems J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Transformations between ecef and enu coordinates J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Ellipsoidal and cartesian coordinates conversion C Vincent Tao and Yong Hu. A comprehensive study of the rational function model for photogrammetric processing Wolfgang Torge and Jürgen Müller. Geodesy R J You. Transformation of cartesian to geodetic coordinates without iterations Jiawei Zhang, Xiangrong Zhang, Junxiao Li, Xu Tang, Tianyang Zhang, Guanchun Wang, Feixiang Liu, and Licheng Jiao. Shadow-aware 3d gaussian splatting for multi-view satellite images Kai Zhang, Jin Sun, and Noah Snavely. Leveraging vision reconstruction pipelines for satellite imagery Qingyuan Zhou, Yue Gong, Weidong Yang, Jiaze Li, Yeqi Luo, Baixin Xu, Shuhao Li, Ben Fei, and Ying He. Mgsr: 2d/3d mutual-boosted gaussian splatting for high-fidelity surface reconstruction under various light conditions Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, and Markus H Gross. Surface splatting NGA. WORLD GEODETIC SYSTEM 1984 - Its Definition and Relationships with Local Geodetic Systems J Sanz Subirana, J M Juan Zornoza, and M Hernández-Pajares Transformations between ecef and enu coordinates <ref:2607. p. 9
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
Improved 3D scene reconstruction for satellite imagery by natively using Rational Polynomial Camera models, which avoids geometric errors introduced by approximating RPC models with perspective or affine camera approximations.
-
Enables accurate projection of Gaussian means and covariances directly through the RPC model during splatting, ensuring a more geometrically consistent rendering process than prior methods.
-
Provides a numerically robust Jacobian-based covariance projection using Jacobians for the nonlinear transformation from global Cartesian coordinates to ellipsoidal geodetic coordinates, which is solver independent.
-
Introduces a metric ray-based depth formulation for RPC cameras, enabling RPC-consistent front-to-back alpha compositing despite the absence of an inherent depth coordinate in RPC models.
-
Allows for the construction of a unified Gaussian Splatting benchmark comparing native RPC, perspective, and affine camera models to directly compare camera model choices against reconstruction error metrics like mean altitude error.
Sources
- EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering
- 3D Surface Reconstruction From Multi-Date Satellite Images
- WildGaussians: 3D Gaussian Splatting in the Wild
- Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs